{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3REYTHOMATRAECWXYH3MR5AO42","short_pith_number":"pith:3REYTHOM","canonical_record":{"source":{"id":"1703.01274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T18:15:32Z","cross_cats_sorted":["cs.HC","cs.RO"],"title_canon_sha256":"fff59ffeb8d9b44358d03cd907984c20909781453a6745344f5b15a4914b2bc8","abstract_canon_sha256":"0009f483b6b0c0e01b3e46bbdb4e0a0e859bf67c08f75f23be93480199035401"},"schema_version":"1.0"},"canonical_sha256":"dc49899dcc04e2020ad7c1f6c8f40ee692813e8dbe0fd6092e7c11fc65d09214","source":{"kind":"arxiv","id":"1703.01274","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01274","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01274v2","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01274","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"3REYTHOMATRA","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3REYTHOMATRAECWX","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3REYTHOM","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3REYTHOMATRAECWXYH3MR5AO42","target":"record","payload":{"canonical_record":{"source":{"id":"1703.01274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T18:15:32Z","cross_cats_sorted":["cs.HC","cs.RO"],"title_canon_sha256":"fff59ffeb8d9b44358d03cd907984c20909781453a6745344f5b15a4914b2bc8","abstract_canon_sha256":"0009f483b6b0c0e01b3e46bbdb4e0a0e859bf67c08f75f23be93480199035401"},"schema_version":"1.0"},"canonical_sha256":"dc49899dcc04e2020ad7c1f6c8f40ee692813e8dbe0fd6092e7c11fc65d09214","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:41.688240Z","signature_b64":"EHY3IHSY4PJ/8xRM0WXS2rZU93mp93EMMNtKvC7UmI4CYQZ6IRcudso9spdJN6D/YFVslGCV6p70qp+RQOqsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc49899dcc04e2020ad7c1f6c8f40ee692813e8dbe0fd6092e7c11fc65d09214","last_reissued_at":"2026-05-18T00:48:41.687826Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:41.687826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.01274","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Or3X8WlOoKVxEFICBU/AyQZZSIerRAMhoKRlqlHAt0VDjUf4QkE+Bbr/3fCuhB+dFUrWsB+5S5MsJCQV73SeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T09:27:36.536357Z"},"content_sha256":"df361f8f9bcbaeca3417f2523979395a56bce99b22bd63d58dc760172066eb8e","schema_version":"1.0","event_id":"sha256:df361f8f9bcbaeca3417f2523979395a56bce99b22bd63d58dc760172066eb8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3REYTHOMATRAECWXYH3MR5AO42","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Actor-Critic Reinforcement Learning with Simultaneous Human Control and Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.RO"],"primary_cat":"cs.AI","authors_text":"Kory W. Mathewson, Patrick M. Pilarski","submitted_at":"2017-03-03T18:15:32Z","abstract_excerpt":"This paper contributes a first study into how different human users deliver simultaneous control and feedback signals during human-robot interaction. As part of this work, we formalize and present a general interactive learning framework for online cooperation between humans and reinforcement learning agents. In many human-machine interaction settings, there is a growing gap between the degrees-of-freedom of complex semi-autonomous systems and the number of human control channels. Simple human control and feedback mechanisms are required to close this gap and allow for better collaboration bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01274","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DT/PTqnF/CoXiW4Jx0o2E/9NyN433BayTjHoVnAUUSArQ6AJO7NvodVrQ27ov1rPo5NAK3vMDGHlfduEVNHSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T09:27:36.536725Z"},"content_sha256":"a51afc733ab808995a4bbeb756eec067329bc86877fcffd47aa329d0bc99cf86","schema_version":"1.0","event_id":"sha256:a51afc733ab808995a4bbeb756eec067329bc86877fcffd47aa329d0bc99cf86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42/bundle.json","state_url":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3REYTHOMATRAECWXYH3MR5AO42/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T09:27:36Z","links":{"resolver":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42","bundle":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42/bundle.json","state":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3REYTHOMATRAECWXYH3MR5AO42/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3REYTHOMATRAECWXYH3MR5AO42","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0009f483b6b0c0e01b3e46bbdb4e0a0e859bf67c08f75f23be93480199035401","cross_cats_sorted":["cs.HC","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T18:15:32Z","title_canon_sha256":"fff59ffeb8d9b44358d03cd907984c20909781453a6745344f5b15a4914b2bc8"},"schema_version":"1.0","source":{"id":"1703.01274","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01274","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01274v2","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01274","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"3REYTHOMATRA","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3REYTHOMATRAECWX","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3REYTHOM","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:a51afc733ab808995a4bbeb756eec067329bc86877fcffd47aa329d0bc99cf86","target":"graph","created_at":"2026-05-18T00:48:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"This paper contributes a first study into how different human users deliver simultaneous control and feedback signals during human-robot interaction. As part of this work, we formalize and present a general interactive learning framework for online cooperation between humans and reinforcement learning agents. In many human-machine interaction settings, there is a growing gap between the degrees-of-freedom of complex semi-autonomous systems and the number of human control channels. Simple human control and feedback mechanisms are required to close this gap and allow for better collaboration bet","authors_text":"Kory W. Mathewson, Patrick M. Pilarski","cross_cats":["cs.HC","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T18:15:32Z","title":"Actor-Critic Reinforcement Learning with Simultaneous Human Control and Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01274","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:df361f8f9bcbaeca3417f2523979395a56bce99b22bd63d58dc760172066eb8e","target":"record","created_at":"2026-05-18T00:48:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0009f483b6b0c0e01b3e46bbdb4e0a0e859bf67c08f75f23be93480199035401","cross_cats_sorted":["cs.HC","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T18:15:32Z","title_canon_sha256":"fff59ffeb8d9b44358d03cd907984c20909781453a6745344f5b15a4914b2bc8"},"schema_version":"1.0","source":{"id":"1703.01274","kind":"arxiv","version":2}},"canonical_sha256":"dc49899dcc04e2020ad7c1f6c8f40ee692813e8dbe0fd6092e7c11fc65d09214","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc49899dcc04e2020ad7c1f6c8f40ee692813e8dbe0fd6092e7c11fc65d09214","first_computed_at":"2026-05-18T00:48:41.687826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:41.687826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EHY3IHSY4PJ/8xRM0WXS2rZU93mp93EMMNtKvC7UmI4CYQZ6IRcudso9spdJN6D/YFVslGCV6p70qp+RQOqsCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:41.688240Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.01274","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df361f8f9bcbaeca3417f2523979395a56bce99b22bd63d58dc760172066eb8e","sha256:a51afc733ab808995a4bbeb756eec067329bc86877fcffd47aa329d0bc99cf86"],"state_sha256":"1847592a3ac7649b9b378925bfbe61eb23197da6e35019b49ebc17b6b2263aaa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZQeYb/QRuPTb3bBv8MLKoV60hIYMU7cbJo46BEPajOI7JBVkGM2Nzw21ozpVTuBu/KOaI8SgXmS42T0LcqbSDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T09:27:36.538753Z","bundle_sha256":"1e813b17202fb773b9a6d43f5cf625e7228e13edc9746264be0a16a4f171f3b4"}}